Scala transformation script to extract plaintext from TEI - Pliny Natural History

gistfile1.scala

import scala.xml.XML
import java.io.FileWriter
import scala.xml.transform.RewriteRule
import scala.xml.Node
import scala.xml.NodeSeq
import scala.xml.Elem
import scala.xml.transform.RuleTransformer
import scala.xml.Text

object TEI extends App {
  
  val xml = XML.loadFile("/home/simonr/Workspaces/pelagios/pelagios3-scripts/tei/Perseus_text_1999.02.0137.xml")
  
  val books = xml \\ "div1"
  
  books.foreach(book => {
    val bookNumber = (book \ "@n").text.toInt
    
    // We're only interested in books 3 - 6 (the geographical ones)
    if (bookNumber > 2 && bookNumber < 7) {
      (book \\ "div2").foreach(chapter => {
        val writer = new FileWriter("book" + bookNumber + "_chapter" + (chapter \ "@n").text + ".txt")
        
        // Remove 'note' tags
        val removeNotes = new RewriteRule {
          override def transform(n: Node): NodeSeq = n match {
            case e: Elem if (e.label.equals("note")) => Text("")
            case e: Elem if (e.label.equals("head")) => Text(e.text + "\n\n")
            case e: Text => Text(e.text.replace("\n", " "))
            case n => n
          }
        }
        
        val cleaned = new RuleTransformer(removeNotes).transform(chapter).text.replaceAll(" +", " ").replace("\n ", "\n").trim()

        writer.write(cleaned)
        writer.flush()
        writer.close()
      })
    }
  })

}